| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 278.09 KB | Adobe PDF |
Advisor(s)
Abstract(s)
In order to improve the performance of Convolutional Neural Networks
(CNN) in the classification of mammographic images, many researchers
choose to apply a normalization method during the pre-processing stage.
In this work, we aim to assess the impact of six different normalization
methods in the classification performance of two CNNs.
Results allow us to concluded that the effect of image normalization
in the performance of the CNNs depends of which network is chosen
to make the lesion classification; besides, the normalization method that
seems to have the most positive impact is the one that subtracts the image
mean and divide it by the corresponding standard deviation (best AUC
mean with CNN-F = 0.786 and with Caffe = 0.790; best run AUC result
was 0.793 with CNN-F and 0.791 with Caffe).
Description
Keywords
Convolutional Neural Networks